[论文解读] Object Recognition in Different Lighting Conditions at Various Angles by Deep Learning Method

Imran Khan Mirani, Tianhua Chen+3 more|arXiv (Cornell University)|Oct 18, 2022

Advanced Neural Network Applications被引用 7

一句话总结

本文提出了一种基于深度学习的物体识别系统，利用卷积神经网络（CNNs）提升在不同光照条件和视角下的鲁棒性。通过端到端学习、权重重用和稀疏连接，该模型在物体比例较小且训练样本有限的情况下实现了更高的准确率，展示了在真实应用中对光照和视角变化的更强适应能力。

ABSTRACT

Existing computer vision and object detection methods strongly rely on neural networks and deep learning. This active research area is used for applications such as autonomous driving, aerial photography, protection, and monitoring. Futuristic object detection methods rely on rectangular, boundary boxes drawn over an object to accurately locate its location. The modern object recognition algorithms, however, are vulnerable to multiple factors, such as illumination, occlusion, viewing angle, or camera rotation as well as cost. Therefore, deep learning-based object recognition will significantly increase the recognition speed and compatible external interference. In this study, we use convolutional neural networks (CNN) to recognize items, the neural networks have the advantages of end-to-end, sparse relation, and sharing weights. This article aims to classify the name of the various object based on the position of an object's detected box. Instead, under different distances, we can get recognition results with different confidence. Through this study, we find that this model's accuracy through recognition is mainly influenced by the proportion of objects and the number of samples. When we have a small proportion of an object on camera, then we get higher recognition accuracy; if we have a much small number of samples, we can get greater accuracy in recognition. The epidemic has a great impact on the world economy where designing a cheaper object recognition system is the need of time.

研究动机与目标

• 开发一种对光照条件和视角变化具有鲁棒性的基于深度学习的物体识别系统。
• 解决现有物体检测方法在光照、遮挡和相机旋转方面表现不佳的局限性。
• 提升识别速度，并增强在真实应用（如自动驾驶和监控）中对外部干扰的兼容性。
• 研究在复杂视觉条件下，物体比例和样本数量对识别准确率的影响。

提出的方法

• 本研究采用卷积神经网络（CNNs）实现端到端的特征学习与物体分类。
• 利用CNNs在权重重用、稀疏连接和分层特征提取方面的固有优势。
• 模型基于检测到的边界框对物体进行分类，置信度分数随物体距离和大小而变化。
• 通过优化小物体比例和有限样本量的训练数据，评估模型的鲁棒性。
• 在多种光照条件和视角下对系统进行评估，以检验其泛化能力。
• 通过不同物体比例和样本数量下的置信度分数与分类准确率来衡量识别性能。

实验结果

研究问题

• RQ1 在不同光照和视角条件下，物体比例如何影响识别准确率？
• RQ2 有限训练样本对模型在复杂视觉条件下的性能有何影响？
• RQ3 基于CNN的系统能否在物体较小或从极端角度观察时仍保持高识别准确率？
• RQ4 光照变化如何影响所提出模型中物体检测的置信度与准确率？
• RQ5 CNN中权重重用与稀疏连接在多大程度上提升了真实世界物体识别任务中的鲁棒性？

主要发现

• 当图像中物体所占比例较小时，模型识别准确率更高，表明对小尺度特征具有更强的敏感性。
• 识别准确率随训练样本数量减少而提升，表明在数据稀缺条件下具备强大的泛化能力。
• 由于CNN的分层特征学习能力，模型对光照变化和视角变化表现出鲁棒性。
• 识别置信度分数显著受物体距离和大小影响，反映出模型对空间上下文的敏感性。
• 端到端学习、权重重用与稀疏连接的结合显著提升了在存在外部干扰的真实环境下的性能。
• 研究证实，物体识别性能对物体比例和样本数量的敏感性高于对光照或视角变化单独影响的敏感性。